© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 120165
    Prev
    Next
    INDEX
    Explanations

    specific terms followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite

    breakdown, covering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prestige
    0.42
     devotes
    0.42
    ौनक
    0.42
     ką
    0.41
     especially
    0.40
     Oriented
    0.40
    法
    0.40
     ose
    0.39
     inclu
    0.39
    ध्याय
    0.39
    POSITIVE LOGITS
    зо
    0.50
     им
    0.50
     Бен
    0.50
     vaporization
    0.47
     काली
    0.47
     ла
    0.47
     մ
    0.46
     बु
    0.46
    дцать
    0.46
     сили
    0.46
    Activations Density 0.001%

    No Known Activations